I think what you're asking for (efficient removal of TTL'd write-once data) is already in the works but not until 2.0 it seems.

https://issues.apache.org/jira/browse/CASSANDRA-5228

-Bryan



On Tue, May 28, 2013 at 1:26 PM, Hiller, Dean <Dean.Hiller@nrel.gov> wrote:
Oh and yes, astyanax uses client side response latency and cassandra does
the same as a client of the other nodes.

Dean

On 5/28/13 2:23 PM, "Hiller, Dean" <Dean.Hiller@nrel.gov> wrote:

>Actually, we did a huge investigation into this on astyanax and cassandra.
> Astyanax if I remember worked if configured correctly but casasndra did
>not so we patched cassandraŠfor some reason cassandra once on the
>co-ordinator who had one copy fo the data would wait for both other nodes
>to respond even though we are CL=QUOROM on RF=3Šwe put in patch for that
>which my teammate is still supposed to submit.  Cassandra should only wait
>for one nodeŠat least I think that is how I remember itŠ.We have it in our
>backlog to get the patch into cassandra.
>
>Previously one slow node would slow down our website but this no longer
>happens to us such that when compaction kicks off on a single node, our
>cluster keeps going strong.
>
>Dean
>
>On 5/28/13 2:12 PM, "Dwight Smith" <Dwight.Smith@genesyslab.com> wrote:
>
>>How do you determine the slow node, client side response latency?
>>
>>-----Original Message-----
>>From: Hiller, Dean [mailto:Dean.Hiller@nrel.gov]
>>Sent: Tuesday, May 28, 2013 1:10 PM
>>To: user@cassandra.apache.org
>>Subject: Re: data clean up problem
>>
>>How much disk used on each node?  We run the suggested < 300G per node as
>>above that compactions can have trouble keeping up.
>>
>>Ps. We run compactions during peak hours just fine because our client
>>reroutes to the 2 of 3 nodes not running compactions based on seeing the
>>slow node so performance stays fast.
>>
>>The easy route is to of course double your cluster and halve the data
>>sizes per node so compaction can keep up.
>>
>>Dean
>>
>>From: cem <cayiroglu@gmail.com<mailto:cayiroglu@gmail.com>>
>>Reply-To: "user@cassandra.apache.org<mailto:user@cassandra.apache.org>"
>><user@cassandra.apache.org<mailto:user@cassandra.apache.org>>
>>Date: Tuesday, May 28, 2013 1:45 PM
>>To: "user@cassandra.apache.org<mailto:user@cassandra.apache.org>"
>><user@cassandra.apache.org<mailto:user@cassandra.apache.org>>
>>Subject: Re: data clean up problem
>>
>>Thanks for the answer.
>>
>>Sorry for the misunderstanding. I tried to say I don't send delete
>>request from the client so it safe to set gc_grace to 0. TTL is used for
>>data clean up. I am not running a manual compaction. I tried that ones
>>but it took a lot of time finish and I will not have this amount of
>>off-peek time in the production to run this. I even set the compaction
>>throughput to unlimited and it didnt help that much.
>>
>>Disk size just keeps on growing but I know that there is enough space to
>>store 1 day data.
>>
>>What do you think about time rage partitioning? Creating new column
>>family for each partition and drop when you know that all records are
>>expired.
>>
>>I have 5 nodes.
>>
>>Cem.
>>
>>
>>
>>
>>On Tue, May 28, 2013 at 9:37 PM, Hiller, Dean
>><Dean.Hiller@nrel.gov<mailto:Dean.Hiller@nrel.gov>> wrote:
>>Also, how many nodes are you running?
>>
>>From: cem
>><cayiroglu@gmail.com<mailto:cayiroglu@gmail.com><mailto:cayiroglu@gmail.c
>>o
>>m<mailto:cayiroglu@gmail.com>>>
>>Reply-To:
>>"user@cassandra.apache.org<mailto:user@cassandra.apache.org><mailto:user@
>>c
>>assandra.apache.org<mailto:user@cassandra.apache.org>>"
>><user@cassandra.apache.org<mailto:user@cassandra.apache.org><mailto:user@
>>c
>>assandra.apache.org<mailto:user@cassandra.apache.org>>>
>>Date: Tuesday, May 28, 2013 1:17 PM
>>To:
>>"user@cassandra.apache.org<mailto:user@cassandra.apache.org><mailto:user@
>>c
>>assandra.apache.org<mailto:user@cassandra.apache.org>>"
>><user@cassandra.apache.org<mailto:user@cassandra.apache.org><mailto:user@
>>c
>>assandra.apache.org<mailto:user@cassandra.apache.org>>>
>>Subject: Re: data clean up problem
>>
>>Thanks for the answer but it is already set to 0 since I don't do any
>>delete.
>>
>>Cem
>>
>>
>>On Tue, May 28, 2013 at 9:03 PM, Edward Capriolo
>><edlinuxguru@gmail.com<mailto:edlinuxguru@gmail.com><mailto:edlinuxguru@g
>>m
>>ail.com<mailto:edlinuxguru@gmail.com>>> wrote:
>>You need to change the gc_grace time of the column family. It defaults to
>>10 days. By default the tombstones will not go away for 10 days.
>>
>>
>>On Tue, May 28, 2013 at 2:46 PM, cem
>><cayiroglu@gmail.com<mailto:cayiroglu@gmail.com><mailto:cayiroglu@gmail.c
>>o
>>m<mailto:cayiroglu@gmail.com>>> wrote:
>>Hi Experts,
>>
>>
>>We have general problem about cleaning up data from the disk. I need to
>>free the disk space after retention period and the customer wants to
>>dimension the disk space base on that.
>>
>>After running multiple performance tests with TTL of 1 day we saw that
>>the compaction couldn't keep up with the request rate. Disks were getting
>>full after 3 days. There were also a lot of sstables that are older than
>>1 day after 3 days.
>>
>>Things that we tried:
>>
>>-Change the compaction strategy to leveled. (helped a bit but not much)
>>
>>-Use big sstable size (10G) with leveled compaction to have more
>>aggressive compaction.(helped a bit but not much)
>>
>>-Upgrade Cassandra from 1.0 to 1.2 to use TTL histograms (didn't help at
>>all since it has key overlapping estimation algorithm that generates %100
>>match. Although we don't have...)
>>
>>Our column family structure is like this:
>>
>>Event_data_cf: (we store event data. Event_id  is randomly generated and
>>each event has attributes like location=london)
>>
>>row                  data
>>
>>event id          data blob
>>
>>timeseries_cf: (key is the attribute that we want to index. It can be
>>location=london, we didnt use secondary indexes because the indexes are
>>dynamic.)
>>
>>row                  data
>>
>>index key       time series of event id (event1_id, event2_id....)
>>
>>timeseries_inv_cf: (this is used for removing event by event row key. )
>>
>>row                  data
>>
>>event id          set of index keys
>>
>>Candidate Solution: Implementing time range partitions.
>>
>>Each partition will have column family set and will be managed by client.
>>
>>Suppose that you want to have 7 days retention period. Then you can
>>configure the partition size as 1 day and have 7 active partitions at any
>>time. Then you can drop inactive partitions (older that 7 days). Dropping
>>will immediate remove the data from the disk. (With proper Cassandra.yaml
>>configuration)
>>
>>Storing an event:
>>
>>Find the current partition p1
>>
>>store to event_data to Event_data_cf_p1
>>
>>store to indexes to timeseries_cff_p1
>>
>>store to inverted indexes to timeseries_inv_cf_p1
>>
>>
>>A time range query with an index:
>>
>>Find the all partitions belongs to that time range
>>
>>Do read starting from the first partition until you reach to limit
>>
>>.....
>>
>>Could you please provide your comments and concerns ?
>>
>>Is there any other option that we can try?
>>
>>What do you think about the candidate solution?
>>
>>Does anyone have the same issue? How would you solve it in another way?
>>
>>
>>Thanks in advance!
>>
>>Cem
>>
>>
>>
>>
>